使用雨水去除技術可以幫助許多戶外視覺應用，使得雨水影像變清晰。在本文中，我們提供了一種自動從雨水影像中找出雨水模板的方法，並利用這些模板更新雨水字典，使雨水字典能學習該張影像的雨水特性。我們也說明如何判別一個區塊是否為雨水區塊的可能性，並依據判別結果修改縮減係數。實驗結果顯示，與現有的方法相比，我們的方法顯示出更好的結果

Using rain removal technique to make a raining image clean can help in many outdoor visual applications. In this paper we present an automatic way to choose rain templates from a given raining image. With these templates, rain dictionary is modified. We also illustrate how to determine the likelihood of a patch being a raining patch. Shrinkage coefficient is modified according to such likelihood. Our method is shown to have better results comparing to existing similar methods.

目錄
第一章	緒論	1
第二章	相關文獻	3
2.1	以影片為主的方法	3
2.2	以單張影像為主的方法	4
2.3	字典學習與稀疏編碼	5
第三章	研究方法	10
3.1	前處理	12
3.1.1	尋找雨水區塊	12
3.1.2	更新雨水字典&編碼輸入影像	14
3.2	取得判別參數	15
3.2.1	block-wise difference	16
3.2.2	pixel-wise difference	19
3.2.3	patch-wise平均與標準差	20
3.2.4	計算patch-wise差值的分布	21
3.2.5	制定參考值	21
3.3	patch判別	22
3.3.1	修正縮減係數	22
3.3.2	去除雨水	24
第四章	實驗結果	26
4.1	更新雨水字典	26
4.2	判別patch	30
4.3	與其他方法比較	34
第五章	結論與未來研究方向	38
參考文獻	40
附錄：英文論文	43

圖目錄
圖 1-1簡易系統流程圖	2
圖 2-1 Kang et al. 系統圖	6
圖 2-2 實驗結果	9
圖 3-1 系統流程圖	11
圖 3-2 雨水區塊	13
圖 3-3 Son et al. 的實驗結果	15
圖 3-4 block-wise difference	17
圖 3-5 block-wise平均與標準差	18
圖 3-6 pixel-wise difference	19
圖 3-7 本文的實驗結果	25
圖 4-1 更新字典對物件輪廓的影響	27
圖 4-2 更新字典對與水的影響	28
圖 4-3 字典更新比較	29
圖 4-4 判別patch的影響	31
圖 4-5 判別patch比較	32
圖 4-6 其他方法比較	35
圖 4-7 其他方法比較	36
圖 5-1 實驗結果	39

表目錄
表 4-1 字典更新比較	30
表 4-2 判別patch比較	34
表 4-3 其他方法比較	37

[1]	K. Garg and S. K. Nayar. Detection and removal of rain from videos. In IEEE Conf. Computer Vision and Pattern Recognition, 2004.
[2]	K. Garg and S. K. Nayar. When does a camera see rain? In IEEE Int’l Conf. Computer Vision, 2005.
[3]	X. Zhang, H. Li, Y. Qi, W. K. Leow, and T. K. Ng. Rain removal in video by combining temporal and chromatic properties. In IEEE Int’l Conf. Multimedia and Expo, 2006
[4]	N. Brewer and N. Liu. Using the shape characteristics of rain to identify and remove rain from video. Lecture Notes Comput. Sci., 2008.
[5]	P. C. Barnum, S. Narasimhan, and T. Kanade. Analysis of rain and snow in frequency space. Int. J. Computer Vision, 2010.
[6]	J. Bossu, N. Hauti`ere, and J.-P. Tarel. Rain or snow detection in image sequences through use of a histogram of orientation of streaks. Int’l. J. Computer Vision, 2011
[7]	S. You, R. T. Tan, R. Kawakami, and K. Ikeuchi. Adherent raindrop detection and removal in video. In CVPR, 2013.
[8]	V. Santhaseelan and V. K. Asari. Utilizing local phase information to remove rain from video. In IJCV, 2014.
[9]	L.-W. Kang, C.-W. Lin, and Y.-H. Fu. Automatic single-image-based rain streaks removal via image decomposition. In IEEE Trans. Image Processing, 2012.
[10]	C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. In IEEE ICCV, 1998.
[11]	J.-H. Kim, C. Lee, J.-Y. Sim, and C.-S. Kim. Single-image deraining using an adaptive nonlocal means filter. In IEEE Int’l Conf. Image Processing, 2013.
[12]	S.-C. Pei, Y.-T. Tsai, and C.-Y. Lee. Removing rain and snow in a single image using saturation and visibility features. In ICME Workshops, IEEE, 2014.
[13]	Y. Luo, Y. Xu, and H. Ji. Removing rain from a single image via discriminative sparse coding. In IEEE Int’l Conf. Computer Vision, 2015.
[14]	Shujian Yu, Weihua Ou. Single image rain streaks removal based on self-learning and structured sparse representation. In IEEE, 2015.
[15]	Chang-Hwan Son, Xiao-Ping Zhang. Rain removal via shrinkage-based sparse coding and learned rain dictionary. In IEEE, 2016.
[16]	Y. Li, R. T. Tan, X. Guo, J. Lu, and M. S. Brown. Rain streak removal using layer priors. In IEEE Int’l Conf. Computer Vision and Pattern Recognition, 2016.
[17]	M. Aharon, M. Elad, and A. M. Bruckstein. The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representation. In IEEE Trans. Signal Process., 2006.
[18]	J. Mairal, F. Bach, J. Ponce, and G. Sapiro. Online learning for matrix factorization and sparse coding. In JMLR, 2010.
[19]	A. Tropp and C. Gilbert. Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit. In IEEE Transactions on Information Theory, 2007.
[20]	D.-Y. Chen, C.-C. Chen, and L.-W. Kang. Visual depth guided color image rain streaks removal using sparse coding. In IEEE Transactions on Circuits and Systems for Video Technology, 2014.
[21]	Y. Luo, Y. Xu, and H. Ji, "Removing rain from a single image via discriminative sparse coding. In. IEEE International Conference on Computer Vision, 2015.
[22]	D. Eigen, D. Krishnan, and R. Fergus. Restoring an image taken through a window covered with dirt or rain. In IEEE International Conference on Computer Vision, 2013.